Dipankar Sarkar
votes For
Require human-in-the-loop oversight for agentic AI systems acting in high-stakes domains
An agent is a set of actions: read a ticket, look up a customer, draft a reply, update a field, send an email, issue a refund. Each action carries different risk. The right question is: What action needs what kind of human approval? [...] Low reversi...more AI Verified source (Oct 8, 2026)